INDEX

Explanations

names of places or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Äįast

-0.16

ãģ¡ãĤĥãĤĵ

-0.16

>&

-0.14

-strokes

-0.14

heimer

-0.14

 oprav

-0.14

_PROVID

-0.14

alars

-0.14

llx

-0.14

lbrace

-0.13

POSITIVE LOGITS

/-

0.16

à¸´à¹Į

0.16

.com

0.16

enville

0.16

 Ã¢

0.15

Bos

0.15

à¸¸à¹Į

0.14

Ø§ØªÙĩ

0.14

ftware

0.14

Activations Density 0.361%

names of places or locations

No Comments

No Known Activations