INDEX

Explanations

specific names and titles related to people and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

weis

-0.16

rax

-0.16

voor

-0.15

ohen

-0.14

Ð³Ñĥ

-0.14

uer

-0.14

ool

-0.13

rys

-0.13

ster

-0.13

POSITIVE LOGITS

Sle

0.19

 Moff

0.15

usercontent

0.15

Til

0.14

 Overs

0.14

-Clause

0.14

owie

0.13

vester

0.13

veal

0.13

 overlay

0.13

Activations Density 0.108%

specific names and titles related to people and locations

No Comments

No Known Activations