INDEX

Explanations

names of individuals, particularly in the context of obituaries or memorials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

nelly

-0.19

ned

-0.18

à¸¥à¸¥

-0.18

ebek

-0.17

mare

-0.17

nel

-0.16

eldon

-0.16

utdown

-0.16

amba

-0.16

omi

-0.15

POSITIVE LOGITS

-wide

0.18

eding

0.17

ot

0.17

ing

0.16

es

0.15

0.14

ol

0.14

en

0.14

yles

0.14

viewer

0.14

Activations Density 0.636%

names of individuals, particularly in the context of obituaries or memorials

No Comments

No Known Activations