INDEX

Explanations

mentions of established processes, protocols, or regulations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ibbon

-0.16

ikel

-0.15

ardin

-0.14

uilder

-0.14

ering

-0.13

liest

-0.13

ylon

-0.13

dn

-0.13

Î´Î¹Î¬

-0.13

-focused

-0.13

POSITIVE LOGITS

 place

0.57

-place

0.42

place

0.40

 Place

0.39

.place

0.38

_place

0.35

Place

0.35

 PLACE

0.35

 inplace

0.33

 pace

0.31

Activations Density 0.032%

mentions of established processes, protocols, or regulations in various contexts

No Comments

No Known Activations