INDEX

Explanations

content related to movies and television

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

loe

-0.16

SBATCH

-0.15

woff

-0.14

ighton

-0.14

ableObject

-0.14

":[{↵

-0.14

swire

-0.14

ingham

-0.14

avis

-0.14

eÄį

-0.14

POSITIVE LOGITS

fik

0.16

ÑĤÐ°Ð»

0.13

pedia

0.13

 Franti

0.13

redi

0.13

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.13

ãĤ´ãĥª

0.13

åĪĻ

0.13

 Barry

0.13

TypeId

0.13

Activations Density 0.251%

content related to movies and television

No Comments

No Known Activations