INDEX

Explanations

references to decision-making and its consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

kte

-0.17

"text

-0.15

Matchers

-0.14

ÏĦÎ¿

-0.14

lico

-0.14

cÃŃ

-0.14

å°¾

-0.14

à¤¿à¤§

-0.14

andid

-0.14

lus

-0.14

POSITIVE LOGITS

 decisions

0.69

 decision

0.66

decision

0.57

 Decision

0.53

Decision

0.51

 choices

0.42

_decision

0.41

åĨ³

0.39

 karar

0.35

 deciding

0.33

Activations Density 0.261%

references to decision-making and its consequences

No Comments

No Known Activations