INDEX

Explanations

references to access and control over resources or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

å¾Ĵ

-0.16

baru

-0.16

ì§ĵ

-0.15

ØªØ§ÙĨ

-0.15

ansen

-0.15

LOAT

-0.15

ISIBLE

-0.15

Ð¾ÑģÑĤÐ°Ð²

-0.15

izzas

-0.15

æ¢¨

-0.14

POSITIVE LOGITS

ability

0.18

ibi

0.17

 access

0.16

sap

0.16

aint

0.16

 gained

0.15

via

0.15

for

0.15

alls

0.15

Activations Density 0.146%

references to access and control over resources or information

No Comments

No Known Activations