INDEX

Explanations

references to feedback in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

abo

-0.17

-regexp

-0.15

uell

-0.14

ysl

-0.14

vÄĽd

-0.14

ktop

-0.14

zet

-0.14

abez

-0.14

ATAB

-0.14

ftime

-0.14

POSITIVE LOGITS

/Instruction

0.19

rix

0.15

_MEM

0.14

Assignable

0.14

æĤ

0.14

aries

0.14

 Feedback

0.14

reas

0.13

Activations Density 0.009%

references to feedback in various contexts

No Comments

No Known Activations