INDEX

Explanations

terms related to opposition and resistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

VIC

-0.16

tron

-0.15

atoria

-0.15

itra

-0.14

illo

-0.14

ATOR

-0.14

appa

-0.14

hurst

-0.13

sco

-0.13

itchens

-0.13

POSITIVE LOGITS

 against

0.18

à¸Ĺà¸²à¸Ļ

0.18

 Against

0.17

ìĤ¬íķŃ

0.15

ors

0.15

enta

0.15

sing

0.15

ably

0.15

alent

0.15

Î½Î±Î½

0.14

Activations Density 0.116%

terms related to opposition and resistance

No Comments

No Known Activations