INDEX

Explanations

terms related to suspicion and suspicion regarding events or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

igham

-0.18

gressor

-0.17

utsch

-0.17

esk

-0.16

icens

-0.15

asha

-0.15

asurer

-0.15

ussen

-0.14

ESA

-0.14

ingham

-0.14

POSITIVE LOGITS

ively

0.19

ably

0.19

ombo

0.15

 Moon

0.15

lessly

0.15

mong

0.15

embr

0.15

oot

0.14

rious

0.14

Activations Density 0.030%

terms related to suspicion and suspicion regarding events or individuals

No Comments

No Known Activations