INDEX

Explanations

historical dates and significant numerical references

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

inger

-0.15

anner

-0.15

-0.14

 residual

-0.14

elters

-0.13

gren

-0.13

ighest

-0.13

isay

-0.13

POSITIVE LOGITS

 aggreg

0.15

forge

0.15

 putas

0.14

 Readonly

0.14

esso

0.14

ãĥ¬ãĥ¼

0.14

sse

0.14

splice

0.14

porno

0.13

PropTypes

0.13

Activations Density 0.014%

historical dates and significant numerical references

No Comments

No Known Activations