INDEX

Explanations

terms related to authoritative guidance or control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lest

-0.18

-0.15

 Ellis

-0.15

 Tarif

-0.15

-0.14

chemy

-0.14

 Taken

-0.14

olle

-0.14

POSITIVE LOGITS

atorial

0.28

ators

0.21

inction

0.21

Vectorizer

0.20

inct

0.19

inary

0.19

à¤¾à¤²à¤¯

0.18

ation

0.17

tape

0.17

ATOR

0.16

Activations Density 0.012%

terms related to authoritative guidance or control

No Comments

No Known Activations