INDEX

Explanations

punctuation marks and symbols typically used in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

akte

-0.16

ickle

-0.16

 PlzeÅĪ

-0.15

erez

-0.15

inct

-0.15

iece

-0.14

 RESPONS

-0.14

arrera

-0.14

ç±

-0.14

ingu

-0.14

POSITIVE LOGITS

 broadly

0.16

eck

0.15

Ø¬Ø§Ø±

0.15

 Caval

0.15

Å

0.15

 principle

0.15

 proof

0.15

 Chow

0.14

 source

0.14

 glue

0.14

Activations Density 0.000%

punctuation marks and symbols typically used in text

No Comments

No Known Activations