INDEX

Explanations

conditional phrases and hypothetical situations

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

ba

-0.17

aths

-0.17

athe

-0.16

Guy

-0.16

ano

-0.15

ouser

-0.15

Guy

-0.14

outu

-0.14

enstein

-0.14

berger

-0.14

POSITIVE LOGITS

.fore

0.14

odash

0.14

.bel

0.14

 Ø§ÙĦØ§Ø³Øª

0.13

.habbo

0.13

_FC

0.13

à¹Ħà¸Ķ

0.13

åºŃ

0.13

ear

0.13

 fresh

0.13

Activations Density 0.037%

conditional phrases and hypothetical situations

No Comments

No Known Activations