INDEX

Explanations

fragments of code or syntax structures within programming code

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

emoc

-0.17

andel

-0.17

heap

-0.15

DOC

-0.14

lest

-0.14

kids

-0.14

å¶

-0.14

_Property

-0.14

Î»Î¬

-0.14

enu

-0.13

POSITIVE LOGITS

ipse

0.16

oulos

0.15

ØªØ²

0.15

 Unidos

0.14

.mc

0.14

bane

0.13

iola

0.13

ailles

0.13

Activations Density 0.029%

fragments of code or syntax structures within programming code

No Comments

No Known Activations