INDEX

Explanations

references to strategies and tactical approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ocz

-0.15

 Wilkinson

-0.15

 Banc

-0.15

ÑĪÑĤ

-0.15

UniqueId

-0.15

ibi

-0.14

ÑĦÑĤ

-0.14

urrences

-0.13

loor

-0.13

Dlg

-0.13

POSITIVE LOGITS

leur

0.16

IGIN

0.15

jom

0.14

lec

0.13

_NOTICE

0.13

pedia

0.13

Gad

0.13

acades

0.13

arto

0.13

deaux

0.12

Activations Density 0.500%

references to strategies and tactical approaches

No Comments

No Known Activations