INDEX

Explanations

negations or expressions of disagreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

geÃ§

-0.15

 Moreno

-0.15

 Mature

-0.15

endra

-0.14

gel

-0.14

 Deferred

-0.14

by

-0.14

-0.13

WARNING

-0.13

 filmy

-0.13

POSITIVE LOGITS

ãģŁãĤī

0.16

Bins

0.15

yg

0.14

tach

0.14

Â£Â£

0.14

tae

0.14

.lu

0.13

/xhtml

0.13

quier

0.13

 Lust

0.13

Activations Density 0.104%

negations or expressions of disagreement

No Comments

No Known Activations