INDEX

Explanations

items or lists in structured formats

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

akt

-0.16

esta

-0.16

 Tham

-0.15

ank

-0.14

vore

-0.14

ovol

-0.14

uyá»ĩn

-0.14

 nhau

-0.13

marca

-0.13

 htons

-0.13

POSITIVE LOGITS

oftware

0.16

¯u

0.16

ospels

0.14

 bullet

0.14

AndPassword

0.14

bib

0.14

âĸį

0.13

Ð°Ð´Ñĥ

0.13

peat

0.13

SocketAddress

0.13

Activations Density 0.019%

items or lists in structured formats

No Comments

No Known Activations