INDEX

Explanations

emotional responses, particularly those related to tension, frustration, and various forms of fear and anger

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.16

hoff

-0.15

nero

-0.15

MIS

-0.14

/html

-0.14

ÅĤe

-0.14

otomy

-0.14

jo

-0.14

esi

-0.13

Ã

-0.13

POSITIVE LOGITS

iman

0.15

erton

0.15

SError

0.15

éĸĢ

0.14

(CancellationToken

0.14

ÑĤÐ¾ÑĢÐ°

0.14

ked

0.14

ãģ¨ãĤĤ

0.14

ibil

0.14

rof

0.14

Activations Density 0.451%

emotional responses, particularly those related to tension, frustration, and various forms of fear and anger

No Comments

No Known Activations