INDEX

Explanations

instances of place names or geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

llx

-0.16

oppins

-0.15

ãģ¤ãģ¶

-0.15

ENC

-0.14

enc

-0.14

.Condition

-0.14

 Ø¬Ø²

-0.14

Î¼Î²

-0.13

iliz

-0.13

Î³Î¿

-0.13

POSITIVE LOGITS

 Grim

0.16

cion

0.15

 Frid

0.15

grave

0.15

earer

0.14

combe

0.14

Ø±ÙĪÙħ

0.14

 unlike

0.13

ameda

0.13

Activations Density 0.009%

instances of place names or geographic locations

No Comments

No Known Activations