INDEX

Explanations

specific phrases or terms occurring frequently in contexts involving public interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bear

-0.15

eyse

-0.15

å¿į

-0.15

éº

-0.15

UCT

-0.14

presso

-0.14

ucc

-0.14

zeÅĦ

-0.14

upp

-0.14

nze

-0.14

POSITIVE LOGITS

 centrally

0.14

 quis

0.14

ileen

0.14

iaz

0.14

adem

0.13

icom

0.13

 sphere

0.13

_OPENGL

0.13

ibe

0.13

izon

0.13

Activations Density 0.027%

specific phrases or terms occurring frequently in contexts involving public interest

No Comments

No Known Activations