INDEX

Explanations

sentences that introduce explanations or justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

unsch

-0.16

ombo

-0.15

çĨĬ

-0.14

iler

-0.14

/antlr

-0.14

ILLISE

-0.14

iÄį

-0.14

inte

-0.14

áº¡o

-0.14

enal

-0.13

POSITIVE LOGITS

why

0.16

yme

0.16

obi

0.15

Cf

0.15

 scrim

0.15

weise

0.15

ifo

0.14

CF

0.14

 Lone

0.14

isky

0.14

Activations Density 0.032%

sentences that introduce explanations or justifications

No Comments

No Known Activations