INDEX

Explanations

references to pop culture events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ansi

-0.16

ÐºÐ°Ð½

-0.15

aise

-0.15

:disable

-0.15

ockey

-0.14

uber

-0.14

Äįen

-0.14

RIPT

-0.14

 Funk

-0.14

POSITIVE LOGITS

atte

0.16

ione

0.15

_triggered

0.15

 mines

0.14

Cir

0.14

 Ð³Ð°Ð»

0.14

inia

0.14

ozem

0.13

wives

0.13

onda

0.13

Activations Density 0.007%

references to pop culture events and figures

No Comments

No Known Activations