INDEX

Explanations

statements related to quantified achievements or metrics in various contexts

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

uhl

-0.17

 embar

-0.15

Zak

-0.14

 sophomore

-0.14

 Ramos

-0.14

Į

-0.14

Ø¦Ø©

-0.14

POSITIVE LOGITS

0.58

 seven

0.56

 seventh

0.53

ä¸ĥ

0.52

 Seven

0.49

-seven

0.49

 Seventh

0.48

 ä¸ĥ

0.48

seven

0.47

VII

0.45

Activations Density 0.094%

statements related to quantified achievements or metrics in various contexts

No Comments

No Known Activations

statements related to quantified achievements or metrics in various contexts

No Comments

No Known Activations