INDEX

Explanations

instances of the word "active" and related forms, indicating a focus on activity or engagement within 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

ming

-0.17

sworth

-0.16

nga

-0.16

ers

-0.15

ately

-0.15

ÏĢÎ»

-0.14

 EXEMPLARY

-0.14

·

-0.14

xit

-0.14

quer

-0.14

POSITIVE LOGITS

/pass

0.25

-active

0.22

ivity

0.20

-duty

0.17

active

0.17

(active

0.17

idade

0.17

/react

0.17

_inactive

0.15

 Active

0.15

Activations Density 0.037%

instances of the word "active" and related forms, indicating a focus on activity or engagement within various contexts

No Comments

No Known Activations