INDEX

Explanations

proper nouns and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

bero

-0.16

ELS

-0.16

Cast

-0.14

caret

-0.14

ahu

-0.14

TG

-0.14

arte

-0.14

 Conj

-0.14

itar

-0.14

POSITIVE LOGITS

 Atomic

0.17

ault

0.15

opc

0.14

.Handled

0.14

_fsm

0.14

ÅĤug

0.14

ortex

0.14

ëĥ¥

0.14

 MÃ©

0.14

urance

0.14

Activations Density 0.409%

proper nouns and place names

No Comments

No Known Activations