INDEX

Explanations

technical programming elements and code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ERO

-0.17

-0.14

å¥

-0.14

SEP

-0.14

inned

-0.14

strap

-0.13

tier

-0.13

ÙħÙĨØ¯

-0.13

olocation

-0.13

 allo

-0.13

POSITIVE LOGITS

irket

0.18

legs

0.16

uch

0.16

erti

0.15

engo

0.15

irus

0.15

uman

0.15

(flow

0.14

 Pais

0.14

izza

0.14

Activations Density 0.018%

technical programming elements and code snippets

No Comments

No Known Activations