INDEX

Explanations

mathematical symbols and notations

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

gli

-0.16

asc

-0.16

ÙħÙĬÙħ

-0.15

 indent

-0.14

ase

-0.14

ahren

-0.14

ijd

-0.14

POSITIVE LOGITS

imes

0.16

ãĤ¿ãĥ³

0.15

rew

0.14

Uy

0.14

 treasury

0.14

imens

0.14

compan

0.14

pie

0.14

uced

0.14

forder

0.14

Activations Density 0.008%

mathematical symbols and notations

No Comments

No Known Activations