INDEX

Explanations

specific names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ã¤Ã¤n

-0.19

ailable

-0.15

Spo

-0.15

allon

-0.14

¥¿

-0.14

.tf

-0.14

 æİ

-0.14

Î³Î¿Ïħ

-0.14

izin

-0.14

 Ø§ÙĦØ´Ø±

-0.14

POSITIVE LOGITS

ses

0.16

fel

0.14

Ð²Ðµ

0.13

 ÙħØªØ®ØµØµ

0.13

dr

0.13

reck

0.13

ë²ķ

0.13

 Ging

0.13

 Advis

0.13

sWith

0.13

Activations Density 0.000%

specific names of individuals

No Comments

No Known Activations