INDEX

Explanations

references to betting strategies and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

obra

-0.18

affle

-0.17

letcher

-0.16

agoon

-0.16

.Modules

-0.16

usan

-0.16

orre

-0.15

]init

-0.15

orro

-0.15

rikes

-0.14

POSITIVE LOGITS

slo

0.18

insk

0.17

iez

0.16

upp

0.16

 junior

0.15

so

0.15

den

0.15

 folk

0.14

 caus

0.14

ä½

0.14

Activations Density 0.037%

references to betting strategies and decision-making processes

No Comments

No Known Activations