INDEX

Explanations

terms related to language structure and grammar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

esser

-0.16

exion

-0.15

atham

-0.15

Ã¡ct

-0.14

ÐµÐµ

-0.14

chl

-0.14

oard

-0.13

etre

-0.13

[opt

-0.13

POSITIVE LOGITS

ismet

0.18

aler

0.16

linger

0.15

aley

0.15

upo

0.14

ÑĢÑĥÐ½

0.14

lingen

0.14

 conven

0.14

alem

0.14

Activations Density 1.048%

terms related to language structure and grammar

No Comments

No Known Activations