INDEX

Explanations

parentheses and quotation marks indicating string or object structures in coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

herits

-0.14

Hao

-0.14

loor

-0.14

rega

-0.13

ttl

-0.13

æª

-0.13

EMENT

-0.13

chalk

-0.13

ĮĴ

-0.13

inha

-0.13

POSITIVE LOGITS

 Excellence

0.15

å¯¾å¿ľ

0.14

 Spit

0.14

ucci

0.14

ode

0.14

 immedi

0.13

 Terr

0.13

ToPoint

0.13

aleigh

0.13

ãĤ

0.13

Activations Density 0.037%

parentheses and quotation marks indicating string or object structures in coding syntax

No Comments

No Known Activations