INDEX

Explanations

phrases indicating actions or ongoing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

uts

-0.14

isans

-0.14

åĽ³

-0.14

_pushButton

-0.13

lernen

-0.13

ilog

-0.13

isan

-0.13

 ÑĤÐ¾Ð³Ð´Ð°

-0.13

heard

-0.13

åĿĬ

-0.13

POSITIVE LOGITS

 Feel

0.46

 feel

0.45

Feel

0.44

feel

0.38

 Enjoy

0.33

 enjoy

0.32

 hope

0.31

 please

0.31

Enjoy

0.30

 Hope

0.30

Activations Density 0.389%

phrases indicating actions or ongoing processes

No Comments

No Known Activations