INDEX

Explanations

references to flashlights and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

reich

-0.18

Sense

-0.15

-transparent

-0.14

anno

-0.14

eway

-0.14

 Sense

-0.14

_crypto

-0.14

antt

-0.14

ovic

-0.13

 Animator

-0.13

POSITIVE LOGITS

ken

0.15

lam

0.14

 night

0.14

asar

0.14

dim

0.14

-light

0.13

tol

0.13

light

0.13

nad

0.13

 Robbins

0.13

Activations Density 0.145%

references to flashlights and their features

No Comments

No Known Activations