INDEX

Explanations

references to specific years

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

owing

-0.16

itÃ¤t

-0.15

sters

-0.14

aters

-0.14

uka

-0.14

ParameterValue

-0.14

hlen

-0.14

iddet

-0.13

ochen

-0.13

imen

-0.13

POSITIVE LOGITS

fare

0.16

ÚĨÙĩ

0.14

 Baxter

0.14

avern

0.14

reur

0.14

FIXME

0.14

ãĢĥ

0.13

opp

0.13

ROLL

0.13

modes

0.13

Activations Density 0.043%

references to specific years

No Comments

No Known Activations