INDEX

Explanations

references to specific organizations, locations, or structured entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

USTER

-0.15

æµª

-0.15

ado

-0.14

Bor

-0.14

jte

-0.14

ache

-0.14

utter

-0.14

uster

-0.14

Benchmark

-0.14

Pul

-0.13

POSITIVE LOGITS

SEMB

0.15

Ð´Ð¸

0.14

furt

0.14

pecies

0.14

Qed

0.14

semblies

0.13

ãĥ¼ãĥĳãĥ¼

0.13

à¸

0.13

cono

0.13

audi

0.13

Activations Density 1.755%

references to specific organizations, locations, or structured entities

No Comments

No Known Activations