INDEX

Explanations

words related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iegel

-0.17

ousse

-0.17

æĢĢ

-0.16

Å¡ak

-0.16

uario

-0.15

uya

-0.14

arters

-0.14

 Schultz

-0.14

uez

-0.14

ruits

-0.14

POSITIVE LOGITS

ores

0.16

abelle

0.15

 Serif

0.15

haled

0.15

 Trad

0.14

 sails

0.14

 Gors

0.14

axes

0.14

buc

0.14

rik

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations