INDEX

Explanations

expressions of negativity or lack, often related to an absence or deficiency

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

kla

-0.15

ehler

-0.15

buz

-0.14

Unnamed

-0.14

ç½

-0.14

rotch

-0.14

PLETED

-0.13

kaar

-0.13

RG

-0.13

Ø°Ø±

-0.13

POSITIVE LOGITS

 harmful

0.18

sil

0.16

 noise

0.16

adden

0.15

 fear

0.15

Fear

0.14

 clutter

0.14

 vulnerability

0.14

apore

0.14

Activations Density 0.261%

expressions of negativity or lack, often related to an absence or deficiency

No Comments

No Known Activations