INDEX

Explanations

expressions of appreciation or recognition for someone's efforts or contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

forward

-0.15

ataka

-0.15

ody

-0.14

berman

-0.14

 misd

-0.14

.fi

-0.14

oppable

-0.14

BuilderInterface

-0.14

lbrace

-0.14

Ãª

-0.14

POSITIVE LOGITS

Tep

0.15

gorm

0.15

 quietly

0.14

 frozen

0.14

 Lever

0.14

sav

0.14

Activations Density 0.000%

expressions of appreciation or recognition for someone's efforts or contributions

No Comments

No Known Activations