INDEX

Explanations

references to television series and episodes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iliar

-0.16

uest

-0.16

ILED

-0.15

lop

-0.15

iling

-0.14

lx

-0.14

hum

-0.14

illaume

-0.14

 natural

-0.13

caling

-0.13

POSITIVE LOGITS

Crystal

0.16

eyse

0.15

/apt

0.15

atrice

0.15

adora

0.14

ÎķÎļ

0.14

antt

0.14

raki

0.14

entic

0.14

 Crystal

0.14

Activations Density 0.005%

references to television series and episodes

No Comments

No Known Activations