INDEX

Explanations

references to specific names or entities, particularly in a context relating to media or research

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð²Ð°Ð¶Ð°

-0.15

iá»ĥn

-0.15

ãģ£ãģ¡

-0.15

/graphql

-0.14

#__

-0.14

 åī

-0.14

ë¦Ń

-0.14

okies

-0.14

 NotImplemented

-0.14

Ð¶ÐµÐ½

-0.14

POSITIVE LOGITS

ork

0.25

ORK

0.22

oro

0.21

orn

0.17

 horn

0.16

Ã¶r

0.16

oron

0.15

 haute

0.15

ORN

0.15

0.14

Activations Density 0.006%

references to specific names or entities, particularly in a context relating to media or research

No Comments

No Known Activations