INDEX

Explanations

occurrences of names and terms related to individuals and significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

å¯Ħ

-0.16

lac

-0.15

strate

-0.15

 tack

-0.14

ooled

-0.14

instr

-0.14

avit

-0.13

.gca

-0.13

irl

-0.13

 &↵

-0.13

POSITIVE LOGITS

ÑĥÑĢÐ½

0.14

minent

0.14

BU

0.14

IPC

0.14

ipc

0.14

 Ð´ÐµÑģÑıÑĤ

0.13

Ã¡tka

0.13

wrapped

0.13

 legisl

0.13

Closure

0.13

Activations Density 0.001%

occurrences of names and terms related to individuals and significant events

No Comments

No Known Activations