INDEX

Explanations

phrases indicating established criteria or benchmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Standard

-0.18

 Standards

-0.18

 Standard

-0.17

_std

-0.16

standard

-0.16

 standard

-0.16

Ø³ØªØ§ÙĨ

-0.16

std

-0.16

onder

-0.16

orman

-0.16

POSITIVE LOGITS

ised

0.51

ization

0.48

ize

0.42

-issue

0.40

izing

0.39

isation

0.38

-setting

0.38

ized

0.37

 deviation

0.35

izes

0.35

Activations Density 0.034%

phrases indicating established criteria or benchmarks

No Comments

No Known Activations