INDEX

Explanations

references to work and related themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

asurer

-0.18

è£ģ

-0.16

contre

-0.16

.fi

-0.15

setQuery

-0.15

ÑĪÑĮ

-0.14

ibr

-0.14

utar

-0.14

oord

-0.14

enberg

-0.14

POSITIVE LOGITS

ç¾¤

0.16

ihan

0.15

amaz

0.15

amer

0.14

isan

0.14

stock

0.14

steen

0.14

rott

0.13

 Valent

0.13

iba

0.13

Activations Density 0.050%

references to work and related themes

No Comments

No Known Activations