INDEX

Explanations

actions related to decision-making or evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Ð¿Ð½

-0.17

hunter

-0.16

TRS

-0.16

riere

-0.16

ovna

-0.15

verting

-0.15

ilities

-0.15

INET

-0.15

spacer

-0.14

opc

-0.14

POSITIVE LOGITS

 hence

0.18

ally

0.18

ants

0.17

 fact

0.17

 conclus

0.16

 absolute

0.16

 finally

0.15

ãģªãĤī

0.15

/cal

0.15

ly

0.15

Activations Density 0.035%

actions related to decision-making or evaluation processes

No Comments

No Known Activations

actions related to decision-making or evaluation processes

No Comments

No Known Activations