INDEX

Explanations

military-related dialogue and commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ð¶Ð¸Ð²

-0.16

_TYPED

-0.15

ffi

-0.15

Ð¸ÑĤÐ¸Ð²

-0.14

åĺĽ

-0.13

rud

-0.13

fut

-0.13

ColumnName

-0.13

ASK

-0.12

ask

-0.12

POSITIVE LOGITS

ibase

0.21

 Bravo

0.21

 Charlie

0.19

ETA

0.19

Alpha

0.18

 Romeo

0.18

Charlie

0.18

eta

0.18

Fo

0.18

ETA

0.17

Activations Density 0.116%

military-related dialogue and commands

No Comments

No Known Activations