INDEX

Explanations

with

np_max-act · gemini-2.0-flash

The neuron detects mentions of “close contact” (and related phrases about contacting or being in contact with someone, especially an infected person).

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

questions related to symptoms and treatments for medical conditions.

oai_token-act-pair · gpt-4o-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_most

-0.06

Fit

-0.06

Outer

-0.06

UB

-0.06

.pixel

-0.06

 Belt

-0.06

ceeded

-0.06

 algum

-0.06

SMP

-0.06

 Likely

-0.06

POSITIVE LOGITS

 declaración

0.07

(*

0.07

_HPP

0.06

controllers

0.06

 overshadow

0.06

_receiver

0.06

<article

0.06

 bodies

0.06

.Context

0.06

 foster

0.06

Activations Density 0.004%

with

The neuron detects mentions of “close contact” (and related phrases about contacting or being in contact with someone, especially an infected person).

questions related to symptoms and treatments for medical conditions.

No Comments

No Known Activations