INDEX

Explanations

references to games and their availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Sunder

-0.17

bek

-0.14

bru

-0.14

ovsky

-0.14

 collaps

-0.14

adian

-0.14

rena

-0.13

 æĻ´

-0.13

intosh

-0.13

Ã¼nst

-0.13

POSITIVE LOGITS

bie

0.16

ppv

0.16

geg

0.15

emy

0.15

/graphql

0.14

iba

0.14

PFN

0.14

pipe

0.14

ou

0.14

typ

0.13

Activations Density 0.000%

references to games and their availability

No Comments

No Known Activations