INDEX

Explanations

geographical locations and associated names

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

 trom

-0.15

okus

-0.14

eses

-0.14

istan

-0.14

caled

-0.14

ureau

-0.14

orners

-0.14

 propos

-0.14

sth

-0.14

loff

-0.14

POSITIVE LOGITS

ä¾į

0.16

ikh

0.16

IVO

0.15

qui

0.14

orate

0.14

lige

0.14

ETIME

0.13

omen

0.13

unge

0.13

LLU

0.13

Activations Density 0.065%

geographical locations and associated names

No Comments

No Known Activations