INDEX

Explanations

mentions of people, particularly in social contexts and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÑĥÐ³

-0.16

queda

-0.15

 flown

-0.15

 Loved

-0.14

 risen

-0.14

itten

-0.14

aret

-0.14

Ã¡d

-0.14

uchen

-0.14

IVEN

-0.14

POSITIVE LOGITS

was

0.33

was

0.28

_was

0.28

Was

0.25

Was

0.25

 were

0.25

did

0.25

 wasn

0.24

saw

0.23

 yesterday

0.21

Activations Density 0.878%

mentions of people, particularly in social contexts and interactions

No Comments

No Known Activations