INDEX

Explanations

references to conflict and resolution, particularly in a historical context

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

 Pell

-0.14

pell

-0.14

Ach

-0.14

Pel

-0.13

Kel

-0.13

-0.12

_HEL

-0.11

ipel

-0.11

RAR

-0.11

Kel

-0.11

POSITIVE LOGITS

al

0.75

als

0.74

ali

0.69

AL

0.68

ale

0.66

ala

0.66

alis

0.65

alen

0.65

ally

0.64

alin

0.63

Activations Density 0.297%

references to conflict and resolution, particularly in a historical context

No Comments

No Known Activations