INDEX

Explanations

relations between family members and various metrics related to their interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Alternate

-0.17

arket

-0.15

epar

-0.15

 alternate

-0.14

atty

-0.14

VN

-0.14

lope

-0.14

ur

-0.14

tp

-0.14

 Alternate

-0.14

POSITIVE LOGITS

itational

0.17

ÃĹ↵↵

0.17

 ÑĤÐ¾Ð¶Ðµ

0.17

ì§¸

0.15

å¤ª

0.15

too

0.15

pgsql

0.15

ãĥ¼ãĥĭ

0.15

bjerg

0.15

_beg

0.15

Activations Density 0.204%

relations between family members and various metrics related to their interaction

No Comments

No Known Activations