INDEX

Explanations

references to personal pronouns and the involvement of people

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

_BP

-0.16

ysz

-0.15

 Mint

-0.15

ESP

-0.15

_OM

-0.15

 mint

-0.15

Ø§ÙĦÙģ

-0.14

ÙıÙĪÙĨ

-0.14

_RG

-0.13

ueur

-0.13

POSITIVE LOGITS

 Heller

0.17

mites

0.17

uggle

0.15

orp

0.14

thr

0.14

enda

0.14

Thr

0.13

kr

0.13

nda

0.13

orney

0.13

Activations Density 0.039%

references to personal pronouns and the involvement of people

No Comments

No Known Activations