INDEX

Explanations

tags or labels associated with content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

asha

-0.17

Ð»ÑıÐ½

-0.16

TriState

-0.16

.xhtml

-0.15

ãģıãĤīãģĦ

-0.15

kaar

-0.15

 Communications

-0.15

umen

-0.15

owie

-0.14

yal

-0.14

POSITIVE LOGITS

duk

0.16

odb

0.16

reative

0.15

Stories

0.15

Words

0.14

 Words

0.14

atile

0.14

eld

0.14

elman

0.14

nip

0.14

Activations Density 0.002%

tags or labels associated with content

No Comments

No Known Activations