INDEX

Explanations

brand names and product model identifiers related to technology and electronics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Weinstein

-0.16

atte

-0.15

maal

-0.14

irut

-0.14

 Dahl

-0.14

mie

-0.14

rello

-0.14

Checkpoint

-0.13

ãģ«ãĤĪ

-0.13

ledon

-0.13

POSITIVE LOGITS

eyse

0.14

).__

0.14

SSERT

0.14

Æ°

0.14

phere

0.13

akt

0.13

lÃ¤

0.13

_ASYNC

0.13

 Smarty

0.13

ĵåĲį

0.13

Activations Density 0.048%

brand names and product model identifiers related to technology and electronics

No Comments

No Known Activations