INDEX

Explanations

information related to film and television acting credits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ì§

-0.15

fug

-0.15

inet

-0.15

á»ĭch

-0.15

 ÙģÙĨ

-0.14

inema

-0.14

ynth

-0.14

 Ð¼Ð°ÑĪÐ¸Ð½

-0.14

.manage

-0.14

apeutics

-0.14

POSITIVE LOGITS

rlen

0.17

aho

0.15

SG

0.14

ocard

0.14

-camera

0.14

Abb

0.13

 prestigious

0.13

$MESS

0.13

Bon

0.13

Activations Density 0.034%

information related to film and television acting credits

No Comments

No Known Activations