INDEX

Explanations

references to pages and document modifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

handling

-0.16

igner

-0.15

/System

-0.14

ystick

-0.14

igne

-0.14

.uni

-0.14

iki

-0.14

isto

-0.13

POSITIVE LOGITS

iesel

0.18

_macros

0.15

aru

0.14

teg

0.14

 Goat

0.14

frey

0.14

arest

0.13

 Poor

0.13

Mocks

0.13

 Pages

0.13

Activations Density 0.083%

references to pages and document modifications

No Comments

No Known Activations