INDEX

Explanations

references to achievements and notable information in a competitive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

RequestBody

-0.15

.extent

-0.14

cha

-0.14

hem

-0.14

íĥĦ

-0.14

.dsl

-0.14

 sockfd

-0.14

CLUDING

-0.14

ContentSize

-0.14

@student

-0.13

POSITIVE LOGITS

wards

0.15

elerik

0.14

 Kendrick

0.14

ngr

0.14

 Gamer

0.14

å¾ª

0.14

ä¸ĬãģĮ

0.14

omik

0.13

arker

0.13

etler

0.13

Activations Density 0.012%

references to achievements and notable information in a competitive context

No Comments

No Known Activations