INDEX

Explanations

elements related to specific attributes or details within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lore

-0.19

rint

-0.14

ertia

-0.14

çĵ¶

-0.13

bart

-0.13

ined

-0.13

mere

-0.13

mÃ¼r

-0.13

POSITIVE LOGITS

ibold

0.22

è¦ļ

0.17

ÄĻk

0.16

agi

0.15

peg

0.15

acman

0.15

ĵåĲį

0.15

aginator

0.15

igaret

0.14

ignKey

0.14

Activations Density 0.054%

elements related to specific attributes or details within a context

No Comments

No Known Activations