INDEX

Explanations

references to entertainment or media entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oin

-0.19

reno

-0.18

ased

-0.15

Ð¾Ð¹Ð½Ð¾

-0.14

hong

-0.14

abr

-0.14

oa

-0.14

é¡

-0.13

mey

-0.13

eca

-0.13

POSITIVE LOGITS

ihu

0.16

tle

0.15

yne

0.15

cp

0.15

.nb

0.15

tile

0.14

iles

0.14

é»

0.14

_usec

0.14

yre

0.14

Activations Density 0.050%

references to entertainment or media entities

No Comments

No Known Activations