INDEX

Explanations

conjunctions and linking words in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ness

-0.17

elage

-0.15

utherford

-0.14

'er

-0.14

bef

-0.14

 Shut

-0.14

ê²

-0.13

arkers

-0.13

arty

-0.13

arness

-0.13

POSITIVE LOGITS

uf

0.17

rok

0.16

vant

0.16

 Stevenson

0.15

Ð½Ð¸Ð¸

0.15

arning

0.15

especially

0.14

atha

0.14

Ð´Ñı

0.14

 Pist

0.14

Activations Density 0.270%

conjunctions and linking words in the text

No Comments

No Known Activations