INDEX

Explanations

key nouns and adjectives indicating importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.15

éĤ£ç§į

-0.15

pard

-0.14

inos

-0.14

raph

-0.14

reib

-0.13

ook

-0.12

uit

-0.12

chem

-0.12

POSITIVE LOGITS

ttp

0.16

pto

0.16

ichel

0.14

ilos

0.14

eyn

0.14

elage

0.14

omite

0.14

InnerText

0.14

ubar

0.13

_tooltip

0.13

Activations Density 0.045%

key nouns and adjectives indicating importance or significance

No Comments

No Known Activations