INDEX

Explanations

formatted strings and error-related messages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

bower

-0.19

 tiáº¿ng

-0.15

.Ticks

-0.14

atcher

-0.14

ilmington

-0.14

rut

-0.13

InputChange

-0.13

 Lodge

-0.13

ruby

-0.13

pau

-0.13

POSITIVE LOGITS

isen

0.17

berman

0.16

aku

0.16

 thesis

0.15

asn

0.14

dek

0.14

ires

0.14

jen

0.14

Activations Density 0.012%

formatted strings and error-related messages

No Comments

No Known Activations