INDEX

Explanations

statements related to structural or functional characteristics of programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ape

-0.16

innen

-0.15

ns

-0.15

-0.14

inker

-0.14

hen

-0.14

ca

-0.14

 bald

-0.14

POSITIVE LOGITS

 Thumb

0.15

ocre

0.15

-thumb

0.15

Ã¹i

0.15

ervas

0.15

Īëĭ¤

0.14

Ð°Ð½Ð¸ÑĨ

0.14

enty

0.14

hores

0.14

ofire

0.14

Activations Density 0.111%

statements related to structural or functional characteristics of programming elements

No Comments

No Known Activations