INDEX

Explanations

references to "mammoth" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

issen

-0.17

issor

-0.16

yw

-0.15

hurst

-0.14

onaut

-0.14

><?

-0.14

Wunused

-0.14

ief

-0.14

gether

-0.14

Ø§ÙĦØ³

-0.14

POSITIVE LOGITS

moth

0.20

bling

0.16

perl

0.15

ny

0.15

uet

0.15

á»ĳi

0.15

bara

0.14

importe

0.14

RIPT

0.14

orial

0.14

Activations Density 0.016%

references to "mammoth" or related terms

No Comments

No Known Activations