INDEX

Explanations

statements of purpose or goals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

xd

-0.15

une

-0.14

edd

-0.14

riting

-0.14

ats

-0.14

als

-0.13

ÐµÐ¼Ñĥ

-0.13

anca

-0.13

ado

-0.13

POSITIVE LOGITS

tw

0.39

 simple

0.26

Tw

0.24

simple

0.23

 semp

0.23

_tw

0.21

ç®Ģåįķ

0.20

 simples

0.20

Tw

0.20

 Simple

0.20

Activations Density 0.045%

statements of purpose or goals

No Comments

No Known Activations