INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron fires on tokens containing the letter‐sequence “gef,” e.g. in identifiers or names like “gef_repository_…” or “Grafana” (with “rafana” triggering “ana”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ober

-0.07

eries

-0.06

experience

-0.06

 UserDao

-0.06

 Lover

-0.06

 від

-0.06

 Он

-0.06

 Morrison

-0.06

 подраз

-0.06

repo

-0.06

POSITIVE LOGITS

 decoding

0.06

ArgumentException

0.06

 sqlCommand

0.06

buster

0.06

_Column

0.06

 posicion

0.06

 userProfile

0.06

 glaciers

0.06

_GENER

0.06

[-

0.06

Activations Density 0.008%

code

The neuron fires on tokens containing the letter‐sequence “gef,” e.g. in identifiers or names like “gef_repository_…” or “Grafana” (with “rafana” triggering “ana”).

No Comments

No Known Activations

code

The neuron fires on tokens containing the letter‐sequence “gef,” e.g. in identifiers or names like “gef_repository_…” or “Grafana” (with “rafana” triggering “ana”).

No Comments

No Known Activations