INDEX

Explanations

terms related to capabilities and functionalities 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

áºŃu

-0.16

Sen

-0.15

usz

-0.14

sen

-0.14

Sen

-0.14

jong

-0.14

 blank

-0.14

Î¯Î½

-0.14

eneration

-0.14

firm

-0.14

POSITIVE LOGITS

ities

0.47

ity

0.43

ties

0.38

idad

0.37

idades

0.36

ty

0.36

idade

0.35

ITY

0.34

ITIES

0.31

iteit

0.30

Activations Density 0.083%

terms related to capabilities and functionalities in various contexts

No Comments

No Known Activations