INDEX

Explanations

references to personal preferences and recommendations, particularly in music and literature

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.scalablytyped

-0.21

hev

-0.17

ÃŃst

-0.16

ucas

-0.15

drv

-0.15

Ø¨Ø¹

-0.15

bler

-0.15

CHANT

-0.14

VertexBuffer

-0.14

raphics

-0.14

POSITIVE LOGITS

Cow

0.16

Cow

0.16

PRI

0.16

assel

0.16

_fwd

0.15

ifu

0.15

nock

0.15

MUX

0.14

izon

0.14

umm

0.14

Activations Density 0.302%

references to personal preferences and recommendations, particularly in music and literature

No Comments

No Known Activations