INDEX

Explanations

references to websites and online content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ansi

-0.18

adows

-0.15

butt

-0.14

chl

-0.14

pto

-0.14

 Blob

-0.14

à¥°

-0.14

outil

-0.14

MESS

-0.14

olia

-0.14

POSITIVE LOGITS

WithValue

0.17

 local

0.16

 Hawth

0.15

en

0.15

 Reader

0.15

Fr

0.14

Reader

0.14

ÐµÐ½Ñĥ

0.14

allas

0.14

ohen

0.14

Activations Density 0.097%

references to websites and online content

No Comments

No Known Activations