INDEX

Explanations

references to relationships and connections between individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

=sub

-0.15

SocketAddress

-0.15

spar

-0.14

 ^{Â°}

-0.14

illard

-0.14

 Sovere

-0.14

stva

-0.14

illery

-0.14

uyáº¿n

-0.14

vailability

-0.13

POSITIVE LOGITS

 side

1.04

 Side

0.86

side

0.83

-side

0.81

Side

0.78

_side

0.75

 sides

0.74

 SIDE

0.73

.side

0.68

SIDE

0.64

Activations Density 0.194%

references to relationships and connections between individuals or entities

No Comments

No Known Activations