INDEX

Explanations

terms related to military and armed forces

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bane

-0.17

æ¿

-0.16

 Pron

-0.15

 retaining

-0.15

iras

-0.15

opy

-0.14

 Shell

-0.14

apan

-0.14

Aub

-0.14

Shell

-0.14

POSITIVE LOGITS

bedo

0.15

otron

0.15

oksen

0.14

 klar

0.14

CLUD

0.14

_Impl

0.14

stad

0.14

0.13

news

0.13

ammen

0.13

Activations Density 0.010%

terms related to military and armed forces

No Comments

No Known Activations