INDEX

Explanations

various forms and variations of the word "ethics" or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ividual

-0.15

ekl

-0.14

ÑĤÑı

-0.14

ActionCreators

-0.14

uces

-0.14

Ãºi

-0.14

apan

-0.14

ByExample

-0.14

itoris

-0.13

odel

-0.13

POSITIVE LOGITS

ters

0.15

reon

0.15

ãĤ±

0.15

andler

0.14

ri

0.14

ush

0.14

soever

0.14

rene

0.14

owe

0.14

0.13

Activations Density 0.021%

various forms and variations of the word "ethics" or related concepts

No Comments

No Known Activations