INDEX

Explanations

expressions of hatred or strong negative sentiments towards individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/latest

-0.17

-0.16

AdapterFactory

-0.16

 mates

-0.15

ddit

-0.15

ces

-0.15

leanup

-0.15

uckle

-0.14

oleans

-0.14

gency

-0.14

POSITIVE LOGITS

irl

0.15

GLE

0.14

rus

0.14

/env

0.14

rypto

0.14

AKE

0.14

yne

0.14

is

0.14

Å¼y

0.14

mis

0.13

Activations Density 0.107%

expressions of hatred or strong negative sentiments towards individuals or groups

No Comments

No Known Activations