INDEX

Explanations

terms related to measurements or assessments 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

MATRIX

-0.17

ÑĪÑĤ

-0.15

endra

-0.15

Lub

-0.15

bjerg

-0.14

radient

-0.14

amu

-0.14

pcodes

-0.14

 LoggerFactory

-0.14

jong

-0.14

POSITIVE LOGITS

imin

0.15

isco

0.14

*__

0.14

icom

0.14

igu

0.14

ernen

0.13

çĵ

0.13

oup

0.13

asion

0.13

Activations Density 0.000%

terms related to measurements or assessments in various contexts

No Comments

No Known Activations