INDEX

Explanations

content related to publication details and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

escal

-0.14

 Morrison

-0.14

esting

-0.14

okol

-0.13

 Morris

-0.13

Affected

-0.13

omes

-0.13

inds

-0.13

ç¦

-0.13

 deposition

-0.13

POSITIVE LOGITS

forge

0.15

etty

0.15

aks

0.15

EFAULT

0.14

ERGY

0.14

icie

0.14

keleton

0.14

ety

0.14

Forge

0.14

TECTED

0.14

Activations Density 0.061%

content related to publication details and literary works

No Comments

No Known Activations