INDEX

Explanations

titles and ratings of television shows or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

obl

-0.16

IFA

-0.14

mesinin

-0.14

PLUS

-0.13

XT

-0.13

ynes

-0.13

 Vict

-0.13

ALER

-0.13

allback

-0.13

 Prem

-0.13

POSITIVE LOGITS

hazi

0.14

pring

0.14

Ð¾Ð²Ð¾

0.14

erset

0.14

_Tis

0.13

enk

0.13

ÑĸÐ¶

0.13

heit

0.13

ROKE

0.13

il

0.13

Activations Density 0.029%

titles and ratings of television shows or movies

No Comments

No Known Activations