INDEX

Explanations

,

np_max-act · gemini-2.0-flash

The neuron is primarily firing on named‐entity tokens—capitalized words like person/place names (e.g. “Wayne,” “Elmhurst”) and temporal/date terms (e.g. “First,” “October,” “November”).

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

 σχ

-0.06

(core

-0.06

~>

-0.06

 Peaks

-0.06

ónica

-0.06

teří

-0.06

 Fellowship

-0.06

.putText

-0.06

[:

-0.06

Flo

-0.06

POSITIVE LOGITS

IGHT

0.08

 офі

0.07

 reim

0.07

좀

0.07

 zipper

0.06

find

0.06

点击

0.06

_receipt

0.06

ες

0.06

Activations Density 0.044%

,

The neuron is primarily firing on named‐entity tokens—capitalized words like person/place names (e.g. “Wayne,” “Elmhurst”) and temporal/date terms (e.g. “First,” “October,” “November”).

No Comments

No Known Activations

,

The neuron is primarily firing on named‐entity tokens—capitalized words like person/place names (e.g. “Wayne,” “Elmhurst”) and temporal/date terms (e.g. “First,” “October,” “November”).

No Comments

No Known Activations