INDEX

Explanations

terms related to iconic or legendary status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

ida

-0.16

chop

-0.15

itan

-0.14

 most

-0.14

up

-0.14

Ø¬ÙĪ

-0.14

ter

-0.14

endale

-0.14

alet

-0.14

POSITIVE LOGITS

ingles

0.18

/original

0.17

âĢĮØªØ±ÛĮÙĨ

0.16

ummer

0.16

/pop

0.16

ziel

0.15

 moments

0.15

ashboard

0.15

Msp

0.15

ulate

0.14

Activations Density 0.046%

terms related to iconic or legendary status

No Comments

No Known Activations