INDEX

Explanations

references to academic citations and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Licensed

-0.17

 McCorm

-0.17

 Progressive

-0.16

rz

-0.15

ãģıãĤĮãĤĭ

-0.14

ramer

-0.14

Licensed

-0.14

orum

-0.14

 Programm

-0.14

ë¦¬ìĿĺ

-0.13

POSITIVE LOGITS

alfa

0.17

umat

0.16

 FindObjectOfType

0.15

çĭ

0.15

inox

0.15

ç

0.14

 semiclass

0.14

/cache

0.14

kit

0.14

sov

0.14

Activations Density 0.002%

references to academic citations and publication details

No Comments

No Known Activations