INDEX

Explanations

words related to advice or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Å¯st

-0.17

neas

-0.16

 Merkez

-0.16

opis

-0.15

oes

-0.15

itorio

-0.15

illery

-0.15

á»Ĺ

-0.15

fid

-0.14

cest

-0.14

POSITIVE LOGITS

sha

0.16

Î¬

0.15

shl

0.15

INET

0.14

VT

0.14

cky

0.14

BeNull

0.14

CALE

0.14

olf

0.14

dete

0.13

Activations Density 0.053%

words related to advice or recommendations

No Comments

No Known Activations