INDEX

Explanations

events involving conflicts or confrontations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.17

.UIManager

-0.16

cratch

-0.15

apter

-0.15

ewis

-0.15

bens

-0.15

fits

-0.15

UIStoryboardSegue

-0.14

è¨ª

-0.14

 unreal

-0.14

POSITIVE LOGITS

raÅ¾

0.16

algo

0.15

ÑĪÐºÐ°

0.14

Lod

0.14

çķ¥

0.14

iez

0.14

èĺ

0.14

:init

0.14

afort

0.13

ãĥ¼ãĥĳ

0.13

Activations Density 0.188%

events involving conflicts or confrontations

No Comments

No Known Activations