INDEX

Explanations

instances of the word "so" used as discourse markers or conjunctions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĨĨ

-0.17

agne

-0.15

udit

-0.15

umont

-0.14

YY

-0.14

 dint

-0.14

ettes

-0.14

ÏĦÎµÏį

-0.14

_simps

-0.14

 Cleanup

-0.14

POSITIVE LOGITS

0.15

 nowhere

0.14

aping

0.14

imd

0.14

ighet

0.13

ÏģÏį

0.13

oldt

0.13

ãģ«ãģĭ

0.13

ÏģÎ¯

0.13

bsub

0.13

Activations Density 0.097%

instances of the word "so" used as discourse markers or conjunctions

No Comments

No Known Activations