INDEX

Explanations

high-frequency words and phrases indicating actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

endor

-0.17

OTE

-0.16

ote

-0.16

itele

-0.16

rada

-0.16

-0.15

ae

-0.15

ke

-0.14

ampo

-0.14

anja

-0.14

POSITIVE LOGITS

 Maver

0.15

Çİ

0.15

Î±ÏģÎ¬

0.14

redicate

0.14

ltra

0.14

çŃ

0.14

apy

0.14

Ã¡u

0.14

oine

0.14

reno

0.14

Activations Density 0.022%

high-frequency words and phrases indicating actions or states

No Comments

No Known Activations