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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Hess

-0.17

orts

-0.16

le

-0.15

feld

-0.15

hammad

-0.14

oeff

-0.14

izzo

-0.14

ssi

-0.14

 Revel

-0.14

hatt

-0.14

POSITIVE LOGITS

å¹²

0.15

ostÃŃ

0.14

defgroup

0.14

 puta

0.13

ica

0.13

=wx

0.13

ctest

0.13

ì§¸

0.13

NaN

0.13

Activations Density 0.017%

references to academic citations and publication details

No Comments

No Known Activations