INDEX

Explanations

references to sports tournaments and match outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ebi

-0.15

ãģ¾ãģ¾

-0.15

preload

-0.14

 sorts

-0.14

gad

-0.14

-lfs

-0.14

shm

-0.14

_CODEC

-0.13

 explan

-0.13

vala

-0.13

POSITIVE LOGITS

ìĥĿ

0.17

jac

0.15

agra

0.14

raf

0.13

ç©

0.13

adena

0.13

ecome

0.13

ĭ

0.13

lux

0.13

anness

0.13

Activations Density 0.001%

references to sports tournaments and match outcomes

No Comments

No Known Activations