INDEX

Explanations

references to code and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

itori

-0.15

ikan

-0.15

irectional

-0.15

alcon

-0.14

oria

-0.14

 progress

-0.14

PEAT

-0.14

ubi

-0.14

 ç¬

-0.14

ertos

-0.14

POSITIVE LOGITS

chers

0.15

 bufsize

0.14

 Fauc

0.14

lif

0.14

 Swinger

0.14

gs

0.14

.feed

0.13

.converter

0.13

ocks

0.13

oose

0.13

Activations Density 0.128%

references to code and programming constructs

No Comments

No Known Activations