INDEX

Explanations

references to a specific location or place

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

iyat

-0.17

oves

-0.15

Ð¾ÑĤÐ¾Ð²

-0.15

iko

-0.15

otch

-0.15

çĴ

-0.15

urdu

-0.15

odial

-0.15

rgan

-0.14

ennes

-0.14

POSITIVE LOGITS

 Metallic

0.17

inger

0.17

omat

0.15

INGER

0.15

ombo

0.15

asant

0.15

ONTAL

0.15

 Carn

0.14

lÃ½

0.14

tf

0.14

Activations Density 0.021%

references to a specific location or place

No Comments

No Known Activations