INDEX

Explanations

substrings related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

_claim

-0.15

avia

-0.15

º

-0.14

ensen

-0.14

 Burning

-0.14

orgh

-0.14

adt

-0.14

arro

-0.14

-0.13

POSITIVE LOGITS

orts

0.15

rani

0.15

.tb

0.14

 ká»·

0.14

ofday

0.14

plit

0.13

-aos

0.13

_TestCase

0.13

Ã¤chst

0.13

apesh

0.13

Activations Density 0.000%

substrings related to entertainment

No Comments

No Known Activations