INDEX

Explanations

occurrences of code structure or syntactic elements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oub

-0.16

-0.15

 walking

-0.15

unc

-0.15

mant

-0.15

osti

-0.14

ichte

-0.14

POSITIVE LOGITS

ÑĸÐ´

0.17

Eb

0.17

hoff

0.16

ÎµÏĤ

0.15

 dÃ¡n

0.15

OAD

0.15

ÑĢÐ°Ð¶Ð´

0.15

ptune

0.14

 else

0.14

iris

0.14

Activations Density 0.054%

occurrences of code structure or syntactic elements in a programming context

No Comments

No Known Activations