INDEX

Explanations

proper nouns and specific identifiers related to characters or entities

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

istrovstvÃŃ

-0.18

(æľ¨

-0.15

spender

-0.15

äººæīį

-0.15

ovny

-0.15

ìĭ±

-0.15

Ð»ÑİÑĩ

-0.15

entar

-0.15

ControlEvents

-0.15

uze

-0.15

POSITIVE LOGITS

oro

0.17

tery

0.16

Ã¶r

0.16

ak

0.16

oret

0.15

oretical

0.15

new

0.14

ring

0.14

Activations Density 0.237%

proper nouns and specific identifiers related to characters or entities

No Comments

No Known Activations