INDEX

Explanations

phrases related to editing and revisions in written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Nam

-0.18

Adj

-0.16

ritz

-0.14

 Trou

-0.14

ole

-0.14

ZERO

-0.14

umen

-0.14

ix

-0.14

_CORE

-0.13

POSITIVE LOGITS

 originals

0.18

ILED

0.17

 contexto

0.16

-www

0.16

vÃ¡

0.15

å®Įæķ´

0.15

 context

0.15

contexts

0.15

elage

0.15

ilis

0.15

Activations Density 0.094%

phrases related to editing and revisions in written content

No Comments

No Known Activations