INDEX

Explanations

references to categories and classifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 danmark

-0.16

ãģ¾ãģŁ

-0.15

holm

-0.15

Nonce

-0.15

among

-0.14

thumb

-0.14

abant

-0.14

ÏĨÎ±

-0.14

elocity

-0.14

anson

-0.14

POSITIVE LOGITS

 Hass

0.15

çļĦæĺ¯

0.15

 normal

0.15

 conventional

0.14

Saw

0.14

 Zimmer

0.13

Hob

0.13

 pert

0.13

",__

0.13

 Prev

0.13

Activations Density 0.192%

references to categories and classifications in various contexts

No Comments

No Known Activations