INDEX

Explanations

occurrences of significant actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Guy

-0.17

 Fell

-0.15

 ÙħØ¨Ø§Ø´

-0.14

Voj

-0.14

ÑĩÐ½Ñĸ

-0.14

iska

-0.14

acen

-0.13

lights

-0.13

POSITIVE LOGITS

andÄ±r

0.20

andum

0.15

erg

0.15

ereal

0.15

rado

0.15

rame

0.15

incident

0.14

empor

0.14

_buff

0.14

 Beaut

0.14

Activations Density 0.009%

occurrences of significant actions or events

No Comments

No Known Activations