INDEX

Explanations

words or phrases indicating obligations, changes, and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

asar

-0.16

ItemAt

-0.16

 eleg

-0.15

cy

-0.15

 mote

-0.14

Ã©f

-0.14

«

-0.14

Î´Î¯

-0.14

cad

-0.14

íķĺìļ°

-0.14

POSITIVE LOGITS

0.16

IRM

0.15

 Josh

0.15

 Brom

0.15

phis

0.15

buz

0.14

cem

0.14

ki

0.14

irm

0.14

ORMAT

0.14

Activations Density 0.003%

words or phrases indicating obligations, changes, and conditions

No Comments

No Known Activations