INDEX

Explanations

terms related to health and safety

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

vale

-0.19

isinde

-0.15

 GrÃ¼

-0.14

uckle

-0.14

pon

-0.14

Fon

-0.14

ARS

-0.14

FileVersion

-0.14

-0.13

bundles

-0.13

POSITIVE LOGITS

.openg

0.17

-ins

0.14

sons

0.14

 Mehmet

0.14

atform

0.13

letic

0.13

Ø±Ø§Øª

0.13

atically

0.13

dna

0.13

Activations Density 0.150%

terms related to health and safety

No Comments

No Known Activations