INDEX

Explanations

commands or suggestions related to actions or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elage

-0.18

deaux

-0.15

TouchUpInside

-0.15

undle

-0.15

-0.14

ovsky

-0.14

unittest

-0.14

omanip

-0.14

inski

-0.14

Delimiter

-0.14

POSITIVE LOGITS

 behold

0.19

ä¾Ľ

0.17

 consider

0.17

0.16

rys

0.15

wy

0.15

 Consider

0.15

ÙĪØ¬

0.15

aves

0.15

 follow

0.14

Activations Density 0.194%

commands or suggestions related to actions or choices

No Comments

No Known Activations