INDEX

Explanations

proper nouns, particularly names of individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

wers

-0.14

upe

-0.14

æľĭ

-0.14

erts

-0.14

usc

-0.14

µ

-0.13

erre

-0.13

IFn

-0.13

ivre

-0.13

POSITIVE LOGITS

kas

0.16

RICT

0.14

 Colon

0.14

fug

0.14

fried

0.13

aging

0.13

stagram

0.13

 æĥ

0.13

rea

0.12

 COMMENTS

0.12

Activations Density 0.075%

proper nouns, particularly names of individuals and organizations

No Comments

No Known Activations