INDEX

Explanations

references to significant events or notable changes in circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rella

-0.14

eless

-0.14

afone

-0.13

ign

-0.13

ir

-0.13

 fate

-0.13

ity

-0.13

POSITIVE LOGITS

ÛĮØ±Ùĩ

0.14

 æ©

0.14

quip

0.14

åĽ

0.13

resume

0.13

.opensource

0.13

)did

0.13

.gf

0.13

ajs

0.13

/member

0.13

Activations Density 1.511%

references to significant events or notable changes in circumstances

No Comments

No Known Activations