INDEX

Explanations

words related to appointments or nominations in positions of authority

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

nze

-0.17

assis

-0.15

rg

-0.14

arer

-0.14

aux

-0.14

mil

-0.14

UBY

-0.14

igne

-0.14

bole

-0.14

±

-0.13

POSITIVE LOGITS

ubbles

0.16

 Woodward

0.15

ÎŃÎ»

0.14

à¤ł

0.14

elerik

0.14

ylie

0.14

 Torch

0.14

ubble

0.13

cco

0.13

ops

0.13

Activations Density 0.077%

words related to appointments or nominations in positions of authority

No Comments

No Known Activations