INDEX

Explanations

references to hierarchical leadership roles or titles within a military context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

_BU

-0.16

iben

-0.15

ugu

-0.15

WEBPACK

-0.15

buz

-0.14

aravel

-0.14

usu

-0.14

asel

-0.14

wicklung

-0.14

ankan

-0.13

POSITIVE LOGITS

avenport

0.19

chaft

0.15

 presence

0.14

cheng

0.14

ÄĽÅĻ

0.14

 Forces

0.14

 Brad

0.14

 Presence

0.14

unc

0.13

ÎµÏĨ

0.13

Activations Density 0.004%

references to hierarchical leadership roles or titles within a military context

No Comments

No Known Activations