INDEX

Explanations

instances of directional and locational phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ssel

-0.16

zin

-0.15

ssue

-0.14

uem

-0.14

ushima

-0.14

utin

-0.14

encil

-0.14

 sounding

-0.14

adena

-0.13

TD

-0.13

POSITIVE LOGITS

aus

0.17

pez

0.15

\Context

0.15

rame

0.15

acha

0.14

 Wonderland

0.14

 PROCUREMENT

0.14

imenti

0.14

Activations Density 0.031%

instances of directional and locational phrases

No Comments

No Known Activations