INDEX

Explanations

references to prominent figures and their contexts in various discussions

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

osten

-0.17

orraine

-0.15

-0.14

byn

-0.14

åĪ°åºķ

-0.14

Î±ÏģÎ¬

-0.14

unter

-0.13

 trom

-0.13

lington

-0.13

à¤¤à¤°

-0.13

POSITIVE LOGITS

queued

0.16

rava

0.15

nemonic

0.15

_UNICODE

0.14

/compiler

0.14

chedulers

0.14

phinx

0.14

 sorte

0.13

 váºŃy

0.13

 similarly

0.13

Activations Density 0.098%

references to prominent figures and their contexts in various discussions

No Comments

No Known Activations