INDEX

Explanations

references to general concepts and ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aze

-0.15

Thrown

-0.15

iffer

-0.14

Wiki

-0.14

PRINTF

-0.13

holm

-0.13

aser

-0.13

plode

-0.13

deaux

-0.13

 bump

-0.13

POSITIVE LOGITS

ilde

0.16

isper

0.16

anlÄ±k

0.15

 Ensemble

0.15

reme

0.14

ÏĥÎ·

0.14

ERA

0.14

IONS

0.14

.updateDynamic

0.14

illum

0.14

Activations Density 0.015%

references to general concepts and ideas

No Comments

No Known Activations