INDEX

Explanations

syntactic markers, special characters, or formatting elements in the text

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

baz

-0.16

ag

-0.15

ace

-0.15

ivals

-0.14

 conscience

-0.14

 area

-0.14

icon

-0.14

angs

-0.14

urally

-0.14

POSITIVE LOGITS

Å¾dy

0.17

ervo

0.16

Ã©is

0.16

edges

0.16

optera

0.16

çī©

0.15

ktop

0.15

utdown

0.15

oppable

0.15

oltip

0.15

Activations Density 0.003%

syntactic markers, special characters, or formatting elements in the text

No Comments

No Known Activations