INDEX

Explanations

characters or entities, likely focusing on names and significant identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

adt

-0.16

embros

-0.15

Ð»ÑĥÐ¶

-0.15

eldo

-0.15

 sclerosis

-0.14

endon

-0.14

Ì§

-0.14

ertia

-0.14

 autob

-0.14

obl

-0.14

POSITIVE LOGITS

iele

0.16

iÄįka

0.15

itou

0.15

 dual

0.14

int

0.14

 Healthy

0.14

ennen

0.14

oni

0.14

ÑĤÐ°Ð»

0.14

.IS

0.13

Activations Density 0.073%

characters or entities, likely focusing on names and significant identifiers

No Comments

No Known Activations