INDEX

Explanations

nouns related to historical structures 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

lage

-0.16

fy

-0.14

zig

-0.14

bang

-0.14

capital

-0.14

aal

-0.14

ÑĩÐµ

-0.14

 Bang

-0.14

ãģĵãĤĵ

-0.14

POSITIVE LOGITS

 çĻ¾

0.15

egie

0.14

\Domain

0.14

éĿ©

0.14

antt

0.14

asic

0.13

çĴĥ

0.13

orny

0.13

 Medieval

0.13

EGIN

0.13

Activations Density 0.053%

nouns related to historical structures and locations

No Comments

No Known Activations