INDEX

Explanations

references to the concept of "spin" or "spin-offs."

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

_Lean

-0.17

inine

-0.16

KG

-0.16

ipple

-0.16

hap

-0.15

Ð°Ð»Ñĥ

-0.15

ikan

-0.15

amt

-0.15

prit

-0.15

uevo

-0.14

POSITIVE LOGITS

-spin

0.15

itzer

0.14

rw

0.14

 orthodox

0.14

ABCDEFGHIJKLMNOP

0.14

 usual

0.13

vu

0.13

chedulers

0.13

Ø·Ùģ

0.13

ondo

0.13

Activations Density 0.013%

references to the concept of "spin" or "spin-offs."

No Comments

No Known Activations