INDEX

Explanations

proximity relationships between subjects and objects in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

/gpl

-0.15

 GPLv

-0.15

Henry

-0.15

apa

-0.15

anch

-0.14

Ð»Ð°Ð²

-0.14

 {{--<

-0.14

iani

-0.14

antha

-0.14

lod

-0.14

POSITIVE LOGITS

ward

0.16

 Forward

0.15

eward

0.15

wards

0.15

 decision

0.14

olec

0.14

/on

0.14

íĳľ

0.14

 Decision

0.14

 Doll

0.14

Activations Density 0.036%

proximity relationships between subjects and objects in descriptions

No Comments

No Known Activations