INDEX

Explanations

terms related to reflexology

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

askell

-0.17

 risk

-0.16

aker

-0.16

osi

-0.15

cott

-0.15

stalk

-0.15

ffects

-0.15

 Weber

-0.14

ersion

-0.14

xae

-0.14

POSITIVE LOGITS

Æ¯á»

0.15

ssa

0.15

shal

0.14

lland

0.14

IMS

0.14

 bidder

0.14

ocup

0.14

ssi

0.14

krom

0.14

ixon

0.14

Activations Density 0.004%

terms related to reflexology

No Comments

No Known Activations