INDEX

Explanations

phrases indicating potential actions or outcomes related to plans, proposals, and mandates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

NECT

-0.17

á»ĳ

-0.15

ifest

-0.14

Äįi

-0.14

icken

-0.14

_FORE

-0.14

Breadcrumb

-0.13

 amen

-0.13

ungen

-0.13

POSITIVE LOGITS

 solution

0.20

solution

0.18

aeper

0.18

 Solution

0.16

 approached

0.15

Solution

0.15

etine

0.15

oul

0.15

 SOLUTION

0.15

 repeat

0.14

Activations Density 0.180%

phrases indicating potential actions or outcomes related to plans, proposals, and mandates

No Comments

No Known Activations