INDEX

Explanations

references to New York City and its surroundings

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

ourke

-0.17

igg

-0.16

.gg

-0.15

asan

-0.15

acies

-0.15

ummer

-0.14

izona

-0.14

inia

-0.14

.echo

-0.14

rok

-0.13

POSITIVE LOGITS

scape

0.17

/world

0.16

-wide

0.14

BI

0.13

jug

0.13

-span

0.13

env

0.13

 Marathon

0.13

PM

0.12

 Gerald

0.12

Activations Density 0.020%

references to New York City and its surroundings

No Comments

No Known Activations