INDEX

Explanations

references to reviews or critiques of art and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 circuit

-0.17

 Circuit

-0.17

-0.16

-0.14

ircuit

-0.14

_cp

-0.13

misc

-0.13

uant

-0.13

ServletRequest

-0.13

POSITIVE LOGITS

utors

0.15

/-

0.14

rol

0.14

Ã¢l

0.14

 Trou

0.14

ksi

0.14

hani

0.13

unal

0.13

SPATH

0.13

arg

0.13

Activations Density 0.313%

references to reviews or critiques of art and media

No Comments

No Known Activations