INDEX

Explanations

references to television shows and their broadcasting 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

anio

-0.17

Ð°ÑĢÐ¾Ð´

-0.15

@qq

-0.15

aea

-0.14

-hooks

-0.14

arse

-0.14

imonial

-0.14

straint

-0.14

_FLUSH

-0.14

à¹Īà¸§à¸¢

-0.14

POSITIVE LOGITS

Esk

0.18

Gem

0.15

uen

0.15

 programming

0.15

ropic

0.14

imet

0.14

 Programming

0.14

_gem

0.14

é©

0.14

 Î¼ÎŃÏĩÏģÎ¹

0.14

Activations Density 0.012%

references to television shows and their broadcasting status

No Comments

No Known Activations