INDEX

Explanations

terms related to obligations and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

dea

-0.17

asto

-0.16

abar

-0.15

perature

-0.15

ibar

-0.14

aur

-0.14

ady

-0.14

chia

-0.14

ory

-0.14

PLICATION

-0.14

POSITIVE LOGITS

/request

0.18

ly

0.17

/common

0.16

inan

0.15

ariat

0.15

Traits

0.14

/app

0.14

LY

0.14

ised

0.14

Activations Density 0.119%

terms related to obligations and recommendations

No Comments

No Known Activations