INDEX

Explanations

references to software and technology-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 EntityState

-0.16

ivan

-0.15

loat

-0.15

enuine

-0.15

ivre

-0.15

à¥įà¤¡à¤²

-0.14

IRA

-0.14

illin

-0.14

Ð½ÑĸÐ²

-0.14

.toolbox

-0.14

POSITIVE LOGITS

Ð°ÑĢÐ¾Ð´

0.15

-hearted

0.14

ì§

0.14

cete

0.14

seau

0.14

errs

0.14

ither

0.14

lete

0.14

ARTH

0.14

ÑĤÐ°Ð±

0.13

Activations Density 0.010%

references to software and technology-related topics

No Comments

No Known Activations