INDEX

Explanations

terms related to various taxonomic and biological classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

overs

-0.18

stash

-0.15

cq

-0.15

 Cunning

-0.14

inv

-0.14

 cerco

-0.14

ugins

-0.13

EMPL

-0.13

ÐµÑģÑĤÐ²

-0.13

bev

-0.13

POSITIVE LOGITS

lopedia

0.27

achment

0.20

enment

0.18

ment

0.17

lope

0.16

 Morav

0.16

angl

0.15

agement

0.15

Î¬Î²

0.15

yme

0.14

Activations Density 0.038%

terms related to various taxonomic and biological classifications

No Comments

No Known Activations