INDEX

Explanations

discussions regarding military interrogation and drone strike policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Stevens

-0.16

çŃĨ

-0.15

ancial

-0.15

.define

-0.15

.Classes

-0.15

 gent

-0.14

ä¸Ī

-0.14

rint

-0.14

 ãĤ¢ãĤ¤

-0.14

chool

-0.13

POSITIVE LOGITS

ownik

0.15

ÄĽÅĻ

0.15

Unt

0.14

Lang

0.14

æľ¯

0.14

oplast

0.14

ADX

0.14

åŃ

0.14

 Lang

0.14

ãĥĥãĥĦ

0.14

Activations Density 0.007%

discussions regarding military interrogation and drone strike policies

No Comments

No Known Activations