INDEX

Explanations

references to various participants or entities within a discussion or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.18

orch

-0.17

orate

-0.16

ëĿ½

-0.14

INDER

-0.14

rana

-0.14

Ð²Ð¸Ð³

-0.14

imbus

-0.14

-0.13

oster

-0.13

POSITIVE LOGITS

LLU

0.15

apons

0.14

 relay

0.14

ëħĢ

0.14

Ã³ng

0.14

Ã¤ng

0.14

lesc

0.14

 pulse

0.13

Dix

0.13

ilm

0.13

Activations Density 0.030%

references to various participants or entities within a discussion or context

No Comments

No Known Activations