INDEX

Explanations

names of individuals or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ecta

-0.16

ç·

-0.14

reib

-0.14

lena

-0.14

_trait

-0.14

Äįin

-0.14

æĢĿæĥ³

-0.13

ket

-0.13

aÃ±

-0.13

etin

-0.13

POSITIVE LOGITS

 éĿ

0.14

idis

0.14

Roh

0.14

phere

0.14

atz

0.13

ignKey

0.12

OffsetTable

0.12

 Ã¶ld

0.12

|M

0.12

 soma

0.12

Activations Density 0.042%

names of individuals or proper nouns

No Comments

No Known Activations