INDEX

Explanations

sentences involving decision-making and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

intl

-0.15

qus

-0.15

Ã¡zi

-0.14

imbus

-0.14

iolet

-0.14

afx

-0.14

USIC

-0.14

Ð³Ð¾Ð²

-0.14

blr

-0.14

YRO

-0.14

POSITIVE LOGITS

opt

0.54

opt

0.47

 choose

0.44

 opted

0.43

 chose

0.42

 opts

0.40

 opting

0.39

Opt

0.38

choose

0.38

 chooses

0.37

Activations Density 0.275%

sentences involving decision-making and recommendations

No Comments

No Known Activations