INDEX

Explanations

references to helpfulness or assistance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

è±

-0.17

oz

-0.16

iro

-0.15

urn

-0.15

 Perr

-0.15

ivo

-0.15

chet

-0.15

FIELDS

-0.14

ixer

-0.14

bsites

-0.14

POSITIVE LOGITS

apan

0.21

upy

0.16

lest

0.15

nesday

0.15

/goto

0.14

enaire

0.14

ening

0.14

venir

0.14

ness

0.14

Activations Density 0.003%

references to helpfulness or assistance in various contexts

No Comments

No Known Activations