INDEX

Explanations

references to error messages and status codes in a programming context

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

 bureau

-0.15

ÄĻk

-0.15

verture

-0.15

 bothering

-0.14

 compression

-0.14

plitude

-0.13

elles

-0.13

ral

-0.13

anca

-0.13

_ENUM

-0.13

POSITIVE LOGITS

ikh

0.15

oplevel

0.15

ServiceProvider

0.15

loyment

0.14

 Guerrero

0.14

/apps

0.14

WX

0.13

iego

0.13

placer

0.13

-gnu

0.13

Activations Density 0.011%

references to error messages and status codes in a programming context

No Comments

No Known Activations