INDEX

Explanations

phrases about decision-making and agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

alus

-0.13

ãģ«ãĤĤ

-0.13

 Sole

-0.13

unb

-0.13

iero

-0.13

ebe

-0.13

itudes

-0.12

iances

-0.12

 justified

-0.12

thinkable

-0.12

POSITIVE LOGITS

 leave

0.51

Leave

0.47

 Leave

0.45

 leaving

0.43

leave

0.43

let

0.42

 letting

0.39

 leaves

0.37

 wait

0.34

LET

0.33

Activations Density 0.359%

phrases about decision-making and agency

No Comments

No Known Activations