INDEX

Explanations

events related to punishment and disciplinary actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

xed

-0.18

kud

-0.16

 planet

-0.15

 Platt

-0.14

rael

-0.14

bud

-0.14

spir

-0.14

planet

-0.14

ighth

-0.14

aland

-0.14

POSITIVE LOGITS

//{{

0.16

 breeds

0.15

iki

0.14

 Tent

0.14

zig

0.14

ÐµÐ·Ð´

0.13

 Verified

0.13

Fro

0.13

 Hanging

0.13

Spo

0.13

Activations Density 0.326%

events related to punishment and disciplinary actions

No Comments

No Known Activations