INDEX

Explanations

instances of affirmation or agreement in dialogue

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

aine

-0.16

uben

-0.16

obili

-0.15

\Module

-0.14

ixel

-0.14

uzzi

-0.14

Host

-0.14

zas

-0.14

uct

-0.14

POSITIVE LOGITS

 Lever

0.15

 Lambert

0.15

 bridge

0.15

arc

0.15

 Spectrum

0.14

Spe

0.14

_TUN

0.14

implicitly

0.14

 cliff

0.14

ãĤ·ãĥªãĥ¼ãĤº

0.13

Activations Density 0.023%

instances of affirmation or agreement in dialogue

No Comments

No Known Activations