INDEX

Explanations

references to specific keys or identifiers in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

al

-0.18

ationToken

-0.15

izio

-0.15

ucci

-0.14

apia

-0.14

mul

-0.14

arians

-0.14

ÑĩÐ¸Ðº

-0.14

apo

-0.14

ization

-0.13

POSITIVE LOGITS

hole

0.23

nes

0.20

chains

0.20

=key

0.20

note

0.19

frames

0.19

chain

0.18

bindings

0.18

logger

0.18

ed

0.18

Activations Density 0.055%

references to specific keys or identifiers in a programming context

No Comments

No Known Activations